New model predicts outcomes in, stratifies patients with recurrent pericarditis

Researchers have recently developed a novel risk-stratification model used to predict clinical remission (CR) in patients with recurrent pericarditis (RP), a complex condition that is associated with morbidity.

“Our model can also aid in stratifying patients, with high discriminative ability,” they said.

A total of 365 consecutive RP patients (mean age 46 years, 56 percent women) from 2012 to 2019 were analysed retrospectively in this study. CR, the primary outcome, was defined as cessation of all anti-inflammatory therapy with complete resolution of symptoms.

The researchers used five machine learning survival models to calculate the possibility of CR within 5 years and stratify patients into high-, intermediate-, and low-risk groups.

Of the eligible patients, 118 (32 percent) achieved CR. The final prediction model included the following factors as the most significant parameters: steroid dependency, total number of recurrences, pericardial late gadolinium enhancement, age, aetiology, sex, ejection fraction, and heart rate.

On the test set, the new model predicted the long-term clinical outcome of RP patients with a C-index of 0.800. It also demonstrated its capacity to stratify patients into low-, intermediate-, and high-risk groups (log-rank test; p<0.0001).

“The use of an explainable machine learning model can aid physicians in making individualized treatment decision in RP patients,” the researchers said.